open-science
A free desktop app that pairs AI research agents with Python/R notebooks, so you describe a research goal in plain language and get code, analysis, figures and reports with traceable provenance, all running locally.
View aipoch/open-science on GitHub- GitHub stars
- 5,523
- Forks
- —
- Language
- TypeScript
Project details
- Repository
- aipoch/open-science
- Licence
- Apache-2.0
- Primary language
- TypeScript
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
Explore by topic
More tools in Learning & research
- namiagent
aa1143 · MIT
An open-source tutorial-and-working-agent combo: start from a minimal 100-line agent loop, add one capability per lesson, end by understanding how mainstream coding…
- frametell
sitor-ai · AGPL-3.0
A local-first desktop app where an AI agent turns one sentence or a document into a narrated, illustrated explainer video you approve step by step.
- papergraph-mcp
lotchuazzz-crypto · MIT
An MCP server that extracts results and proof evidence from math papers so AI agents can plan reading order without guessing.
- ai-engineering-from-scratch
rohitg00 · MIT
A free, open-source course that walks you through building modern AI systems from scratch, 511 lessons spanning LLMs, RAG, agents and transformers.